Federated Learning in Vehicular Networks: A Review of Emerging Trends and Future Directions

The integration of Federated Learning (FL) into vehicular networks (VANETs) represents a significant advancement in transportation technologies. This novel, distributed machine learning approach enhances VANETs by utilizing decentralized data, ensuring privacy, and minimizing data transmission burdens. This paper provides a comprehensive review of the emerging trends and future directions of FL in VANETs, highlighting its potential to improve vehicular networking and applications. It extensively addresses critical issues of privacy, security, and incentivization within VANET environments, proposing novel solutions and identifying challenges such as resource allocation, big data management, and balancing communication with computation overheads. By analyzing these aspects in detail and forecasting future trends and applications, this review establishes a foundation for ongoing research and development in this evolving field.